Huajie Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Huajie Wu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Fu Zhang
The University of Hong Kong
6 shared publications - Wenyi Liu
Department of Mechanical Engineering, University of Hong Kong, Pokfulam, Hong Kong, China
3 shared publications Fangcheng Zhu
Mechatronics and Robotic Systems (MaRS) Laboratory Department of Mechanical Engineering University of Hong Kong Hong Kong China
2 shared publicationsFanze Kong
Department of Mechanical Engineering, The University of Hong Kong, Pokfulam, China
2 shared publicationsWei Xu
Department of Mechanical Engineering, The University of Hong Kong, Pokfulam, China
2 shared publicationsYihang Li
Department of Mechanical Engineering, The University of Hong Kong, Pokfulam, China
2 shared publications
Latest Publications
- Open Access
- 10 November 2026
- Published by Wiley in Advanced Intelligent Systems
Flying Through Cluttered and Dynamic Environments With Light Detection and Ranging
Navigating unmanned aerial vehicles (UAVs) through cluttered and dynamic environments is a persistent and significant challenge, particularly when high‐speed obstacles are involved. This article presents a comprehensive light detection and ranging‐based system designed to enable UAVs to effectively avoid various moving obstacles, with a specific focus on high‐speed obstacles, in complex environments. Leveraging the high computational efficiency of its perception and planning modules, the system operates in real time with low latency, even when constrained by limited onboard computing resources. For dynamic environment perception, we incorporate the previously developed M‐detector into the system and develop a dynamic environment perception module, which ensures robust perception of moving objects. To address the challenge of dynamic environment planning, we propose an integrated planning and control framework, referred to as DynIPC. DynIPC anticipates the future trajectories of dynamic objects, enabling proactive avoidance of high‐speed obstacles. The proposed system is validated through both simulations and real‐world experiments. In simulation tests, the system consistently outperforms state‐of‐the‐art baselines across multiple metrics, including success rate, time consumption, average flight time, and maximum velocity. In real‐world trials, the system successfully navigates through cluttered environments such as forests, avoiding multiple moving obstacles along its path with a success rate of 85% in a low latency.
- 10 November 2026
- Published by Wiley in Advanced Intelligent Systems
Open AccessFlying Through Cluttered and Dynamic Environments With Light Detection and Ranging
Navigating unmanned aerial vehicles (UAVs) through cluttered and dynamic environments is a persistent and significant challenge, particularly when high‐speed obstacles are involved. This article presents a comprehensive light detection and ranging‐based system designed to enable UAVs to effectively avoid various moving obstacles, with a specific focus on high‐speed obstacles, in complex environments. Leveraging the high computational efficiency of its perception and planning modules, the system operates in real time with low latency, even when constrained by limited onboard computing resources. For dynamic environment perception, we incorporate the previously developed M‐detector into the system and develop a dynamic environment perception module, which ensures robust perception of moving objects. To address the challenge of dynamic environment planning, we propose an integrated planning and control framework, referred to as DynIPC. DynIPC anticipates the future trajectories of dynamic objects, enabling proactive avoidance of high‐speed obstacles. The proposed system is validated through both simulations and real‐world experiments. In simulation tests, the system consistently outperforms state‐of‐the‐art baselines across multiple metrics, including success rate, time consumption, average flight time, and maximum velocity. In real‐world trials, the system successfully navigates through cluttered environments such as forests, avoiding multiple moving obstacles along its path with a success rate of 85% in a low latency.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 2, 753-767
LiDAR-Based Quadrotor Autonomous Inspection System in Cluttered Environments
In recent years, autonomous unmanned aerial vehicle (UAV) technology has seen rapid advancements, significantly improving operational efficiency and mitigating risks associated with manual tasks in domains such as industrial inspection, agricultural monitoring, and search-and-rescue missions. Despite these developments, existing UAV inspection systems encounter two critical challenges: limited reliability in complex, unstructured, and GNSS-denied environments, and a pronounced dependency on skilled operators. To overcome these limitations, this study presents a LiDAR-based UAV inspection system employing a dual-phase workflow: human-in-the-loop inspection and autonomous inspection. During the human-in-the-loop phase, untrained pilots are supported by autonomous obstacle avoidance, enabling them to generate 3D maps, specify inspection points, and schedule tasks. Inspection points are then optimized using the Traveling Salesman Problem (TSP) to create efficient task sequences. In the autonomous phase, the quadrotor autonomously executes the planned tasks, ensuring safe and efficient data acquisition. Comprehensive field experiments conducted in various environments, including slopes, landslides, agricultural fields, factories, and forests, confirm the system’s reliability and flexibility. Results reveal significant enhancements in inspection efficiency, with autonomous operations reducing trajectory length by up to 40% and flight time by 57% compared to human-in-the-loop operations. These findings underscore the potential of the proposed system to enhance UAV-based inspections in safety-critical and resource-constrained scenarios.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 2, 753-767
LiDAR-Based Quadrotor Autonomous Inspection System in Cluttered Environments
In recent years, autonomous unmanned aerial vehicle (UAV) technology has seen rapid advancements, significantly improving operational efficiency and mitigating risks associated with manual tasks in domains such as industrial inspection, agricultural monitoring, and search-and-rescue missions. Despite these developments, existing UAV inspection systems encounter two critical challenges: limited reliability in complex, unstructured, and GNSS-denied environments, and a pronounced dependency on skilled operators. To overcome these limitations, this study presents a LiDAR-based UAV inspection system employing a dual-phase workflow: human-in-the-loop inspection and autonomous inspection. During the human-in-the-loop phase, untrained pilots are supported by autonomous obstacle avoidance, enabling them to generate 3D maps, specify inspection points, and schedule tasks. Inspection points are then optimized using the Traveling Salesman Problem (TSP) to create efficient task sequences. In the autonomous phase, the quadrotor autonomously executes the planned tasks, ensuring safe and efficient data acquisition. Comprehensive field experiments conducted in various environments, including slopes, landslides, agricultural fields, factories, and forests, confirm the system’s reliability and flexibility. Results reveal significant enhancements in inspection efficiency, with autonomous operations reducing trajectory length by up to 40% and flight time by 57% compared to human-in-the-loop operations. These findings underscore the potential of the proposed system to enhance UAV-based inspections in safety-critical and resource-constrained scenarios.
- Open Access
- 11 August 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 7411
Slope inspection under dense vegetation using LiDAR-based quadrotors
Landslides pose significant threats to residents' safety and daily lives. To mitigate such risks, flexible debris-resisting barriers are constructed and regularly inspected, a task known as slope inspection. Traditional manual inspections are costly and difficult due to steep terrains and dense vegetation. Unmanned aerial vehicle (UAV) equipped with LiDAR and cameras offers high mobility, making them well-suited for slope inspections. However, existing UAV solutions lack comprehensive frameworks to handle dense vegetation, including robust localization, high-precision mapping, small and dynamic obstacle avoidance, and cluttered under-canopy navigation. To address these challenges, we develop a LiDAR-based quadrotor with a comprehensive software system. Our quadrotor features assisted obstacle avoidance, enabling it to autonomously avoid intricate obstacles while executing pilot commands. Field experiments conducted in collaboration with the Hong Kong Civil Engineering and Development Department demonstrate our quadrotor's ability to avoid small obstacles and maneuver in dense vegetation, validating its practical potential for slope inspection.
- 11 August 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 7411
Open AccessSlope inspection under dense vegetation using LiDAR-based quadrotors
Landslides pose significant threats to residents' safety and daily lives. To mitigate such risks, flexible debris-resisting barriers are constructed and regularly inspected, a task known as slope inspection. Traditional manual inspections are costly and difficult due to steep terrains and dense vegetation. Unmanned aerial vehicle (UAV) equipped with LiDAR and cameras offers high mobility, making them well-suited for slope inspections. However, existing UAV solutions lack comprehensive frameworks to handle dense vegetation, including robust localization, high-precision mapping, small and dynamic obstacle avoidance, and cluttered under-canopy navigation. To address these challenges, we develop a LiDAR-based quadrotor with a comprehensive software system. Our quadrotor features assisted obstacle avoidance, enabling it to autonomously avoid intricate obstacles while executing pilot commands. Field experiments conducted in collaboration with the Hong Kong Civil Engineering and Development Department demonstrate our quadrotor's ability to avoid small obstacles and maneuver in dense vegetation, validating its practical potential for slope inspection.
- 21 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (1) , 88-95
Large-Scale Multi-Session Point-Cloud Map Merging
This paper introduces LAMM, an open-source framework for large-scale multi-session 3D LiDAR point cloud map merging. LAMM can automatically integrate sub-maps from multiple agents carrying LiDARs with different scanning patterns, facilitating place feature extraction, data association, and global optimization in various environments. Our framework incorporates two key novelties that enable robust, accurate, large-scale map merging. The first novelty is a temporal bidirectional filtering mechanism that removes dynamic objects from 3D LiDAR point cloud data. This eliminates the effect of dynamic objects on the 3D map model, providing higher-quality map merging results. The second novelty is a robust and efficient outlier removal algorithm for detected loop closures. This algorithm ensures a high recall rate and a low false alarm rate in position retrieval, significantly reducing outliers in repetitive environments during large-scale merging. We evaluate our framework using various datasets, including KITTI, HeLiPR, WildPlaces, and a self-collected colored point cloud dataset. The results demonstrate that our proposed framework can accurately merge maps captured by different types of LiDARs and data acquisition devices across diverse scenarios.
- 21 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (1) , 88-95
Large-Scale Multi-Session Point-Cloud Map Merging
This paper introduces LAMM, an open-source framework for large-scale multi-session 3D LiDAR point cloud map merging. LAMM can automatically integrate sub-maps from multiple agents carrying LiDARs with different scanning patterns, facilitating place feature extraction, data association, and global optimization in various environments. Our framework incorporates two key novelties that enable robust, accurate, large-scale map merging. The first novelty is a temporal bidirectional filtering mechanism that removes dynamic objects from 3D LiDAR point cloud data. This eliminates the effect of dynamic objects on the 3D map model, providing higher-quality map merging results. The second novelty is a robust and efficient outlier removal algorithm for detected loop closures. This algorithm ensures a high recall rate and a low false alarm rate in position retrieval, significantly reducing outliers in repetitive environments during large-scale merging. We evaluate our framework using various datasets, including KITTI, HeLiPR, WildPlaces, and a self-collected colored point cloud dataset. The results demonstrate that our proposed framework can accurately merge maps captured by different types of LiDARs and data acquisition devices across diverse scenarios.
- Open Access
- 5 March 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1
Publisher Correction: Moving event detection from LiDAR point streams
- 5 March 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1
Open AccessPublisher Correction: Moving event detection from LiDAR point streams
- Top Cited PapersOpen Access
- 6 January 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-14
Moving event detection from LiDAR point streams
In dynamic environments, robots require instantaneous detection of moving events with microseconds of latency. This task, known as moving event detection, is typically achieved using event cameras. While light detection and ranging (LiDAR) sensors are essential for robots due to their dense and accurate depth measurements, their use in event detection has not been thoroughly explored. Current approaches involve accumulating LiDAR points into frames and detecting object-level motions, resulting in a latency of tens to hundreds of milliseconds. We present a different approach called M-detector, which determines if a point is moving immediately after its arrival, resulting in a point-by-point detection with a latency of just several microseconds. M-detector is designed based on occlusion principles and can be used in different environments with various types of LiDAR sensors. Our experiments demonstrate the effectiveness of M-detector on various datasets and applications, showcasing its superior accuracy, computational efficiency, detection latency, and generalization ability.
- 6 January 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-14
Top Cited PapersOpen AccessMoving event detection from LiDAR point streams
In dynamic environments, robots require instantaneous detection of moving events with microseconds of latency. This task, known as moving event detection, is typically achieved using event cameras. While light detection and ranging (LiDAR) sensors are essential for robots due to their dense and accurate depth measurements, their use in event detection has not been thoroughly explored. Current approaches involve accumulating LiDAR points into frames and detecting object-level motions, resulting in a latency of tens to hundreds of milliseconds. We present a different approach called M-detector, which determines if a point is moving immediately after its arrival, resulting in a point-by-point detection with a latency of just several microseconds. M-detector is designed based on occlusion principles and can be used in different environments with various types of LiDAR sensors. Our experiments demonstrate the effectiveness of M-detector on various datasets and applications, showcasing its superior accuracy, computational efficiency, detection latency, and generalization ability.